From 76e9cd7f24f6b175e4cce85082647403266ed233 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 3 Jun 2016 23:43:34 +0700 Subject: [PATCH] [loc] Add support for another URL schema and simplify --- youtube_dl/extractor/libraryofcongress.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index d311f9946..a5f22b204 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -13,8 +13,8 @@ from ..utils import ( class LibraryOfCongressIE(InfoExtractor): IE_NAME = 'loc' IE_DESC = 'Library of Congress' - _VALID_URL = r'https?://(?:www\.)?loc\.gov/item/(?P[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P[0-9]+)' + _TESTS = [{ 'url': 'http://loc.gov/item/90716351/', 'md5': '353917ff7f0255aa6d4b80a034833de8', 'info_dict': { @@ -25,7 +25,10 @@ class LibraryOfCongressIE(InfoExtractor): 'duration': 0, 'view_count': int, }, - } + }, { + 'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -34,13 +37,12 @@ class LibraryOfCongressIE(InfoExtractor): media_id = self._search_regex( (r'id=(["\'])media-player-(?P.+?)\1', r']+id=(["\'])uuid-(?P.+?)\1', - r']+data-uuid=(["\'])(?P.+?)\1'), + r']+data-uuid=(["\'])(?P.+?)\1', + r'mediaObjectId\s*:\s*(["\'])(?P.+?)\1'), webpage, 'media id', group='id') - data = self._parse_json( - self._download_webpage( - 'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id, - video_id), + data = self._download_json( + 'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id, video_id)['mediaObject'] derivative = data['derivatives'][0] @@ -77,7 +79,7 @@ class LibraryOfCongressIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'duration': duration, 'view_count': view_count, 'formats': formats,